CodeFault/Unsloth-Qwen3.6-27B-NVFP4-GGUF
Not comparable yet vs unsloth/Qwen3.6-27B-NVFP4. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (590 of 1968/1322 match), usually an architecture llama.cpp's name map doesn't cover yet.